GPU-aided servers are widely used to accelerate the increasing computing workload on edge network. However, massive computing requests can cause delays in transmission and processing at edge servers, leading to long response time and high system energy consumption. Moreover, in distributed scenarios, GPUs from different vendors can hardly communicate directly through the network. As a rare open-source GPU architecture, Vortex has been emerged to enable an FPGA accelerator to serve as a PCIe-based soft GPU. On this basis, Vortex GPUs in our edge acceleration architecture further integrate the low-latency RDMA function. Compared with the original Vortex GPU-aided servers cluster, our preliminary study shows that our Vortex GPU cluster is fast, scalable, and energy-efficient.